This project thoroughly examines health-related trends utilizing a diverse set of data points. The variables under scrutiny include gender, age, hypertension, heart disease, work type, settlement characteristics, average glucose level, body mass index, weight class, activity status, and blood glucose group. Through meticulous data analysis, the aim is to derive valuable insights into the interplay of these factors and their collective impact on overall health. This study holds the potential to inform targeted interventions and strategies for health improvement tailored to specific demographic and lifestyle segments.
I utilized a Kaggle dataset comprising details like ID, gender, age, hypertension, marital status, work type, residence, average glucose level, BMI, and smoking status. I employed Microsoft Excel for thorough data cleaning and analysis, integrating DAX functions. I crafted visualizations through Microsoft Power BI, organizing the analysis into distinct phases: data cleaning, DAX functions application, visualization, insights, and actionable recommendations.
Prior to delving into the analysis, a crucial prerequisite is ensuring the dataset's cleanliness and reliability. The data cleaning phase encompasses addressing missing values, rectifying inconsistencies, and formatting the data for seamless analysis. In this project, I meticulously curated the dataset to guarantee the precision and integrity of my findings.
In the initial phase of my analysis, I strategically handled missing values by systematically excluding non-essential columns with significant empty cells. Prioritizing clarity, I employed formatting enhancements such as bolding headers and reordering the dataset. Numerical values underwent precision adjustments, employing number formatting to reduce decimals. Delving deeper, I leveraged DAX functions to derive essential key performance indicators (KPIs) crucial for a comprehensive analysis. Focused on clarity, I meticulously renamed specific headers, aiming to establish a dataset that fosters a thorough understanding and sets the stage for a robust analytical exploration.
Data Analysis Using DAX Functions
By utilizing DAX functions, specifically IF(AND), IF(OR), and IF, I effectively created additional columns to categorize individuals according to weight class, activity status, and blood glucose group. This strategic enhancement enriches the depth of my analysis, offering valuable insights into key parameters that are essential for a thorough comprehension of the dataset.
Using Pivot Table For Better Aggregation And Analysis
Utilizing pivot tables, a comprehensive analysis of the population's susceptibility to diabetes was conducted, categorized by gender and settlement. The data reveals that within the male demographic, 331 individuals are diabetic in urban areas and 299 in rural regions. Additionally, 2408 urban men and 2471 rural men exhibit normal blood glucose levels, with 256 urban and 247 rural men classified as prediabetic. The total count of diabetic men is 630, while 4879 and 503 men fall into the normal and prediabetic categories, respectively.
Shifting focus to the female cohort, 321 women in urban settlements and 348 in rural areas are diabetic. Furthermore, 3983 urban women and 4006 rural women showcase normal blood glucose levels, with 340 urban and 322 rural women classified as prediabetic. The cumulative count indicates 669 diabetic women, alongside 7989 healthy women and 662 prediabetic women.
A noteworthy observation emerges as the number of healthy women surpasses that of men across blood glucose groups. Additionally, the prevalence of the normal blood glucose group in rural settlements exceeds that in urban areas. These insights lay the foundation for a more profound exploration of variables influencing the health of individuals within this population.
DATA MODELING AND VISUAL INSIGHTS WITH POWER BI
In the context of this analysis, the imperative role of data modeling in Power BI cannot be overstated. This intricate process has proven instrumental in cultivating a meticulously structured foundation, a paramount element in facilitating the extraction of meaningful insights. The personalized nature of this data modeling endeavor has allowed for a tailored approach, ensuring that the nuances of the analysis are captured with precision.
In this analysis, the population size is 15k, with 1729 occurrences of hypertension. A stacked column chart highlights the cardiovascular health comparison between urban and rural settlements, revealing lower heart disease and hypertension in rural areas. A TreeMap illustrates weight class distribution: 7k obese, 5k overweight, and 3k normal individuals.
A pie chart showcases average glucose levels by blood group: 1.15M normal, 0.29M diabetic, 0.2M prediabetic, and 0.1M undefined. A line and stacked column chart indicate increased heart disease susceptibility in aging men compared to women, emphasizing age-related health implications.
A line chart explores how activity status affects heart diseases, revealing higher hypertension in females despite activity levels. It underscores the need to consider various factors like nutrition, genetics, and weight for precise health assessments.
A scatter plot depicts the total population by gender, weight class, and age, highlighting female variability in weight class. Cards display an average BMI of 30.19, and a slicer using work type enhances data relevance across analyses in this comprehensive data analysis report.
Based on the insights gleaned from the analysis, several recommendations can be proposed:
These recommendations aim to guide targeted interventions, promoting overall health and well-being within the analyzed population.
In conclusion, the comparative study on health disparities across settlements has unveiled distinct patterns in diabetes prevalence and hypertension, contributing to cardiovascular health issues. Urban areas, notably among men, exhibit elevated rates, emphasizing the imperative need for targeted health interventions in these regions. The gender-specific variations underscore the necessity of tailoring health strategies to address unique challenges.
Furthermore, the observed contrast in normal blood glucose levels between urban and rural settlements prompts a deeper inquiry into the underlying factors driving these disparities. This analysis furnishes invaluable insights, offering a roadmap for addressing health inequalities and guiding the implementation of targeted interventions. The findings aim to enhance overall health outcomes in both urban and rural communities, contributing to a more nuanced understanding of health dynamics across diverse settlements.